nationalflag

Results 8 comments of nationalflag

Why so many bounding box?

same issue

trained models in pytorch

Thanks! I‘m very expect for it!

剪枝后准确率和速率

剪枝了之后precision没变，recall竟然上升了那么多，，是因为yolo3本身对你的项目过拟合么

Why antelopev2 not buffalo_l?

主要是提人脸特征的模型不同，不知道是否是有对比

安装opecv带gstreamer mpp硬解码

用appsink取缓存比只是解码播放要多耗很多cpu资源啊， @luqinlive 请问你最后怎么解决的呢？

n_augment

Should I decrease the complexity of the model to decrease parameters and avoid overfitting when I set n_augment=0?

n_augment

Yes. I try to implement your algorithm on my own and my model's parameters are no more than yours, but my model seems to overfit because the validation error increases...

n_augment

The reconstruction error — second term in your loss function